AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Dynamically Constructed (PO)MDPs for Adaptive Robot Planning

Shiqi Zhang, Piyush Khandelwal, Peter Stone

AAAI 2017 · Reinforcement learning › MDPs and planning · approach: POMDP policy optimization · 25 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
dynamically construct POMDP with reward reasoning (iCORPP) instead of hand-coded static model (CORPP)shopping request identification · Task 1 delivery mistakesmistakes per item/roomImproved
remove unavailable items from the POMDP dynamicallyiCORPP · Task 1 shopping with item unavailabilityaccuracy and overall reward: states/actions 37,50 -> 18,29 with 3 items unavailableImproved
set cautious reward values [30,-30] instead of [20,-20] (ablation)iCORPP · Task 1 delivery mistakescautiousness of behavior: [20,-20] -> [30,-30]Mixed
adaptive MDP reconstruction vs fixed cached policies when walker blocks routerobot navigation · Task 2, loc0-loc2travel time (s): about 250 -> about 110Improved
iCORPP vs CORPP on other start-goal pairsrobot navigation · Task 2, other position pairstravel timeNo clear effect
iCORPP vs CORPP early in trialsrobot navigation · Task 2 overall timetotal time per trialNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy